bochka vs Blaxel
Both give every sandbox its own kernel. bochka gives you a whole Linux machine with a real disk and a faster CPU, while Blaxel is built to sleep in seconds and wake up with its memory intact.
Where bochka stands out
A whole Linux machine
A bochka sandbox has systemd, real SSH, raw TCP and /dev/kvm, so you can run an Android emulator or a VM inside it. Blaxel's Firecracker guests have no nested virtualization and no native SSH.
A faster CPU
On the same Node.js build-and-test benchmark at 4 vCPU and 8 GB, bochka ran 26.69 runs per second and Blaxel 19.48. That is about 1.4 times the work in the same time.
A disk that stays, and agents built in
Your files sit on a real disk that is snapshotted every minute, not in memory. Claude Code, Codex and other agents come installed, and you drive agents inside from outside with one API to prompt, steer and read events.
The companies and products
bochka
bochka.xyz runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.
You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.
- Isolation
- Full VM per sandbox, own kernel
- Regions
- EU: Germany, Finland, France
Blaxel
Blaxel is a San Francisco company that runs cloud infrastructure for AI agents, and since September 2026 it is part of Baseten.
You get sandboxes, batch jobs, MCP server hosting and a model gateway. Each sandbox is a Firecracker microVM with its own kernel that drops to standby when nothing is connected and resumes in under 25 ms with its memory and running processes. It is built for agent products that start many sandboxes and want them asleep most of the time.
- Headquarters
- San Francisco, founded 2024
Which use cases each one fits
For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “3rd cheapest of 367” means 2 of the other 366 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.
| Use case and its workload | bochka: price rank | Blaxel: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Both fit, but bochka adds nested virtualization for Android emulators and a real disk, where Blaxel keeps files in memory unless you attach a volume. | 3rd cheapest of 367 $634 a month | 10th cheapest of 367 $2,373 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Blaxel's sleep in seconds and wake on request suits mostly idle assistants, and bochka keeps them on a full VM with a disk that stays. | 5th cheapest of 366 $657 a month | 12th cheapest of 366 $2,832 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Blaxel is the better pick here: short runs that sleep right away and resume in milliseconds are what it is built for. | 186th of 345, with limits $2,000 a month | 14th cheapest of 345 $144 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month bochka fits 300 users at once on a self-serve plan, while Blaxel's public tiers stop at 200 at once before you talk to sales. | Cheapest of 361 $209 a month | 101st of 361, with limits $926 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 34th of 360, with limits $2,000 a month | 77th of 360, with limits $4,378 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month bochka starts a fresh VM per task from a named snapshot, while Blaxel's public tiers cap how many run at once at 200. | 10th cheapest of 364 $200 a month | 136th of 364, with limits $704 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month | 4th cheapest of 377 $86 a month | 57th cheapest of 377 $431 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB bochka is a plain machine you SSH into and leave on, while Blaxel has no native SSH. | 18th cheapest of 368 $26 a month | 265th of 368, with limits $114 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Both run a desktop and a browser, and bochka streams a 60fps desktop you can embed in your app. | 6th cheapest of 369 $200 a month | 14th cheapest of 369 $634 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 7th cheapest of 367 $200 a month | 16th cheapest of 367 $317 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 6th cheapest of 346 $90 a month | 16th cheapest of 346 $215 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 71st of 338, with limits $1,800 a month | 147th of 338, with limits $4,292 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month Both fit: bochka gives root with raw TCP and nftables, and Blaxel adds domain-level egress rules on the provider side. | 2nd cheapest of 360 $200 a month | 3rd cheapest of 360 $217 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Can't run it | Can't run it |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Can't run it | Can't run it |
Key features
| Feature | bochka | Blaxel |
|---|---|---|
| Isolation | Full VM, own kernel, on dedicated AMD Ryzen 9 9950X hosts | Firecracker microVM, own kernel |
| Nested virtualization | Yes: /dev/kvm, so Android emulators and VMs run inside | No: Firecracker guests do not get /dev/kvm |
| SSH and systemd | Real SSH, root and systemd | Root, terminal through the bl connect command, no native SSH |
| Disk | A real disk that stays, snapshotted every minute and on stop | Files live in memory (about half the RAM); one block volume can be attached at creation |
| Sleep and wake | Stop keeps the disk and costs nothing; resume boots the VM again | Standby a few seconds after the last connection, wakes in under 25 ms with memory and processes |
| Fork | Fork a running sandbox (disk) | Fork with memory and running processes (private preview) |
| Images | Templates from named snapshots, shareable by code; no Dockerfile images | Custom images built from Docker images |
| Docker inside | Yes | Yes, with a Docker-in-sandbox image |
| Inbound traffic | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; own IPv6 or IPv4 | Preview URL per port, public or token-protected; no raw TCP or public IP |
| Outbound rules | Open internet; filter inside the VM with nftables | Domain allow and deny lists, method and path rules, static egress IPs |
| Secret proxy | Real keys never enter the sandbox; model providers and any HTTPS API you register | Proxy fills secrets into outbound HTTPS requests; sandbox never sees them (public preview) |
| Built-in agents | Claude Code, Codex, OpenCode, pi and more, driven by a prompt, steer and events API | Claude Code image you drive from its terminal or your own harness |
| Regions | EU only: Germany, Finland, France | US (Oregon, North Virginia), London, Frankfurt |
| Cost controls | Spend limits and a per-sandbox usage API | Per-sandbox cost and usage API |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | SOC 2 |
Every feature Battleships tracks (43)
| Feature | bochka | Blaxel |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | Yes |
| Nested virtualization | Yes | No |
| Root | Yes | Yes |
| Systemd | Yes | No |
| Desktop GUI | Yes | Yes |
| Browser | Yes | Yes |
| Computer-use API | Yes | Yes |
| SSH | Yes | No |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | Yes |
| Automatic snapshots | Yes | Yes |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | Yes |
| Memory fork | No | Yes |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No | Yes |
| Wake on request | No | Yes |
| HTTPS preview URLs | Yes | Yes |
| Raw TCP inbound | Yes | No |
| Public IPv4 | No | No |
| Egress allowlist | No | Yes |
| Secret proxy | Yes | Yes |
| Secret proxy for any API | Yes | Yes |
| Preinstalled agents | Yes | Yes |
| Agent harness API | Yes | No |
| MCP server | No | Yes |
| GPU | No | No |
| Windows | No | No |
| Arm64 | No | No |
| Self-hosting | No | No |
| BYOC | No | Yes |
| Open source | No | No |
| Scoped API keys | Yes | Yes |
| Spend limits | Yes | No |
| Usage per sandbox (API) | Yes | Yes |
| Audit logs | No | Not published |
| SSO | No | Yes |
| SOC 2 | No | Yes |
| HIPAA | No | Yes |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Yes |
Performance
Both ran the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU and 8 GB in the same run on September 29, 2026. bochka did 26.69 runs per second and Blaxel 19.48. Higher is better, and the bochka number comes from its standard dedicated Ryzen 9 9950X hosts.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Blaxel measured on: Sandbox (active time, RAM-only pricing, CPU bundled).
Pricing in five scenarios
Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario.
| Scenario | bochka, a month | Blaxel, a month |
|---|---|---|
| One coding agent, workdays 4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days | $20 · $20/mo | $33 · Pay-as-you-go Tier 1 |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $120 · Pay-as-you-go Tier 1 |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $317 · $20/mo × 3 seats | $1,489 · Pay-as-you-go Tier 1 |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $200 · $100/mo × 2 seats | $396 · Pay-as-you-go Tier 2 · with limits |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $2,000 · $2000/mo · with limits | $876 · Pay-as-you-go Tier 2 · with limits |
bochka: Your plan payment (from $20 a month) is all usage credit, billed per second while a machine runs. A stopped sandbox costs nothing and keeps its disk.
Blaxel: Blaxel charges for allocated RAM per second while a sandbox is active, with CPU included (8 GB comes with 4 cores). In standby you pay only snapshot storage, and volumes are billed on their full size.
Limits in those scenarios
Blaxel's self-serve tiers allow 10, 50 or 200 sandboxes at once, and sandboxes in standby count toward that limit, so the 300-user and 1,000-job scenarios need a sales tier. bochka's plans allow 100 to 2,000 at once, but it limits how many machines start per minute, so 1,000 jobs at the same moment get queued. On Blaxel, the lower tiers also delete sandboxes after 7 or 30 days, and only Tier 2 and up keep them for good.
| Scenario | bochka | Blaxel |
|---|---|---|
| One coding agent, workdays | None that bite | None that bite |
| One agent that never stops | None that bite | None that bite |
| 50 agents in parallel | None that bite | None that bite |
| Sandboxes for your users | None that bite |
|
| 1,000 short jobs at once |
|
|
Which one should you use?
Use Blaxel when
your sandboxes sit idle most of the time and must wake in milliseconds with their memory, or must run in the US.
- Sleeps in seconds, wakes in milliseconds. Useful if your sandboxes sit idle most of the time: one sleeps seconds after the last connection and wakes in under 25 ms.
- Network rules on the provider side. Blaxel can limit a sandbox to chosen domains, down to methods and paths, and give it static egress IPs.
- US and UK regions. Blaxel runs in Oregon and North Virginia as well as London and Frankfurt.
Use bochka when
your agents do real work for hours: builds, tests, Docker and emulators on a whole Linux machine with a real disk, a faster CPU and agents built in.
- A whole Linux machine. Without /dev/kvm an Android emulator or a VM does not start at all. Without native SSH, tools that expect it, like editors and scp, need a workaround through bl connect.
- A faster CPU. Agents spend most of their time waiting on installs, builds and tests. On Blaxel each of those waits about 1.4 times as long, and you pay for the waiting.
- A disk that stays, and agents built in. Blaxel keeps files in memory, about half the RAM, so a big repo and its dependencies can fill it unless you attach a volume at creation. And without a driving API you build the agent harness yourself.
Questions people ask
Is bochka cheaper than Blaxel?
In four of the five scenarios we priced, bochka costs less: for one coding agent on workdays it is $20 against $33, and for 50 agents in parallel $317 against $1,489. For 1,000 short jobs at once Blaxel is cheaper ($876 against $2,000), though neither fits that scenario on a self-serve plan. Blaxel only bills while a connection is open, so a workload that disconnects often pays less than these numbers.
Is Blaxel a real VM or a container?
A real VM: each Blaxel sandbox is a Firecracker microVM with its own kernel. bochka is also a VM with its own kernel, but a full one, with systemd and nested virtualization.
Can I run Docker or an Android emulator on Blaxel?
Docker, yes, with its Docker-in-sandbox image. An Android emulator needs /dev/kvm, which Firecracker guests do not get, while bochka exposes /dev/kvm inside every sandbox.
Does a bochka sandbox keep its memory when it stops?
No. bochka keeps the disk and reboots on resume, so files and installed packages stay but running processes do not. Blaxel saves memory and processes in standby and resumes them.
What happened to Blaxel after Baseten?
Blaxel joined Baseten on September 10, 2026. Baseten says the product and the support team stay the same and features keep shipping.
Where do bochka and Blaxel run?
bochka runs only in the EU, in Germany, Finland and France, with EU data residency. Blaxel runs in Oregon, North Virginia, London and Frankfurt.
Start a sandbox
Install the CLI, then run bochka new.
Product preview
More comparisons
- bochka vs E2B
- bochka vs Daytona
- bochka vs Modal
- bochka vs Vercel Sandbox
- bochka vs Runloop
- bochka vs Tensorlake
- bochka vs Cloudflare Sandbox
- bochka vs Agent 37
- bochka vs exe.dev
- bochka vs Oracle Cloud
- bochka vs IONOS Cloud
- bochka vs Browser Use
- E2B vs Blaxel
- Daytona vs Blaxel
- Modal vs Blaxel
- Vercel Sandbox vs Blaxel
- Cloudflare Sandbox vs Blaxel
- Blaxel vs Runloop
- Blaxel vs Tensorlake
- Blaxel vs Morph Cloud